/* An implementation of the new I/O lib as defined by PEP 3116 - "New I/O" Classes defined here: UnsupportedOperation, BlockingIOError. Functions defined here: open(). Mostly written by Amaury Forgeot d'Arc */ #include "Python.h" #include "pycore_abstract.h" // _PyNumber_Index() #include "pycore_initconfig.h" // _PyStatus_OK() #include "pycore_long.h" // _PyLong_IsNegative() #include "pycore_pyerrors.h" // _PyErr_ChainExceptions1() #include "pycore_pystate.h" // _PyInterpreterState_GET() #include "_iomodule.h" #ifdef HAVE_SYS_TYPES_H #include <sys/types.h> #endif /* HAVE_SYS_TYPES_H */ #ifdef HAVE_SYS_STAT_H #include <sys/stat.h> #endif /* HAVE_SYS_STAT_H */ #ifdef MS_WINDOWS #include <windows.h> #endif PyDoc_STRVAR(module_doc, "The io module provides the Python interfaces to stream handling. The\n" "builtin open function is defined in this module.\n" "\n" "At the top of the I/O hierarchy is the abstract base class IOBase. It\n" "defines the basic interface to a stream. Note, however, that there is no\n" "separation between reading and writing to streams; implementations are\n" "allowed to raise an OSError if they do not support a given operation.\n" "\n" "Extending IOBase is RawIOBase which deals simply with the reading and\n" "writing of raw bytes to a stream. FileIO subclasses RawIOBase to provide\n" "an interface to OS files.\n" "\n" "BufferedIOBase deals with buffering on a raw byte stream (RawIOBase). Its\n" "subclasses, BufferedWriter, BufferedReader, and BufferedRWPair buffer\n" "streams that are readable, writable, and both respectively.\n" "BufferedRandom provides a buffered interface to random access\n" "streams. BytesIO is a simple stream of in-memory bytes.\n" "\n" "Another IOBase subclass, TextIOBase, deals with the encoding and decoding\n" "of streams into text. TextIOWrapper, which extends it, is a buffered text\n" "interface to a buffered raw stream (`BufferedIOBase`). Finally, StringIO\n" "is an in-memory stream for text.\n" "\n" "Argument names are not part of the specification, and only the arguments\n" "of open() are intended to be used as keyword arguments.\n" "\n" "data:\n" "\n" "DEFAULT_BUFFER_SIZE\n" "\n" " An int containing the default buffer size used by the module's buffered\n" " I/O classes. open() uses the file's blksize (as obtained by os.stat) if\n" " possible.\n" ); /* * The main open() function */ /*[clinic input] module _io _io.open file: object mode: str = "r" buffering: int = -1 encoding: str(accept={str, NoneType}) = None errors: str(accept={str, NoneType}) = None newline: str(accept={str, NoneType}) = None closefd: bool = True opener: object = None Open file and return a stream. Raise OSError upon failure. file is either a text or byte string giving the name (and the path if the file isn't in the current working directory) of the file to be opened or an integer file descriptor of the file to be wrapped. (If a file descriptor is given, it is closed when the returned I/O object is closed, unless closefd is set to False.) mode is an optional string that specifies the mode in which the file is opened. It defaults to 'r' which means open for reading in text mode. Other common values are 'w' for writing (truncating the file if it already exists), 'x' for creating and writing to a new file, and 'a' for appending (which on some Unix systems, means that all writes append to the end of the file regardless of the current seek position). In text mode, if encoding is not specified the encoding used is platform dependent: locale.getencoding() is called to get the current locale encoding. (For reading and writing raw bytes use binary mode and leave encoding unspecified.) The available modes are: ========= =============================================================== Character Meaning --------- --------------------------------------------------------------- 'r' open for reading (default) 'w' open for writing, truncating the file first 'x' create a new file and open it for writing 'a' open for writing, appending to the end of the file if it exists 'b' binary mode 't' text mode (default) '+' open a disk file for updating (reading and writing) ========= =============================================================== The default mode is 'rt' (open for reading text). For binary random access, the mode 'w+b' opens and truncates the file to 0 bytes, while 'r+b' opens the file without truncation. The 'x' mode implies 'w' and raises an `FileExistsError` if the file already exists. Python distinguishes between files opened in binary and text modes, even when the underlying operating system doesn't. Files opened in binary mode (appending 'b' to the mode argument) return contents as bytes objects without any decoding. In text mode (the default, or when 't' is appended to the mode argument), the contents of the file are returned as strings, the bytes having been first decoded using a platform-dependent encoding or using the specified encoding if given. buffering is an optional integer used to set the buffering policy. Pass 0 to switch buffering off (only allowed in binary mode), 1 to select line buffering (only usable in text mode), and an integer > 1 to indicate the size of a fixed-size chunk buffer. When no buffering argument is given, the default buffering policy works as follows: * Binary files are buffered in fixed-size chunks; the size of the buffer is chosen using a heuristic trying to determine the underlying device's "block size" and falling back on `io.DEFAULT_BUFFER_SIZE`. On many systems, the buffer will typically be 4096 or 8192 bytes long. * "Interactive" text files (files for which isatty() returns True) use line buffering. Other text files use the policy described above for binary files. encoding is the name of the encoding used to decode or encode the file. This should only be used in text mode. The default encoding is platform dependent, but any encoding supported by Python can be passed. See the codecs module for the list of supported encodings. errors is an optional string that specifies how encoding errors are to be handled---this argument should not be used in binary mode. Pass 'strict' to raise a ValueError exception if there is an encoding error (the default of None has the same effect), or pass 'ignore' to ignore errors. (Note that ignoring encoding errors can lead to data loss.) See the documentation for codecs.register or run 'help(codecs.Codec)' for a list of the permitted encoding error strings. newline controls how universal newlines works (it only applies to text mode). It can be None, '', '\n', '\r', and '\r\n'. It works as follows: * On input, if newline is None, universal newlines mode is enabled. Lines in the input can end in '\n', '\r', or '\r\n', and these are translated into '\n' before being returned to the caller. If it is '', universal newline mode is enabled, but line endings are returned to the caller untranslated. If it has any of the other legal values, input lines are only terminated by the given string, and the line ending is returned to the caller untranslated. * On output, if newline is None, any '\n' characters written are translated to the system default line separator, os.linesep. If newline is '' or '\n', no translation takes place. If newline is any of the other legal values, any '\n' characters written are translated to the given string. If closefd is False, the underlying file descriptor will be kept open when the file is closed. This does not work when a file name is given and must be True in that case. A custom opener can be used by passing a callable as *opener*. The underlying file descriptor for the file object is then obtained by calling *opener* with (*file*, *flags*). *opener* must return an open file descriptor (passing os.open as *opener* results in functionality similar to passing None). open() returns a file object whose type depends on the mode, and through which the standard file operations such as reading and writing are performed. When open() is used to open a file in a text mode ('w', 'r', 'wt', 'rt', etc.), it returns a TextIOWrapper. When used to open a file in a binary mode, the returned class varies: in read binary mode, it returns a BufferedReader; in write binary and append binary modes, it returns a BufferedWriter, and in read/write mode, it returns a BufferedRandom. It is also possible to use a string or bytearray as a file for both reading and writing. For strings StringIO can be used like a file opened in a text mode, and for bytes a BytesIO can be used like a file opened in a binary mode. [clinic start generated code]*/ static PyObject * _io_open_impl(PyObject *module, PyObject *file, const char *mode, int buffering, const char *encoding, const char *errors, const char *newline, int closefd, PyObject *opener) /*[clinic end generated code: output=aefafc4ce2b46dc0 input=cd034e7cdfbf4e78]*/ { … } /*[clinic input] _io.text_encoding encoding: object stacklevel: int = 2 / A helper function to choose the text encoding. When encoding is not None, this function returns it. Otherwise, this function returns the default text encoding (i.e. "locale" or "utf-8" depends on UTF-8 mode). This function emits an EncodingWarning if encoding is None and sys.flags.warn_default_encoding is true. This can be used in APIs with an encoding=None parameter. However, please consider using encoding="utf-8" for new APIs. [clinic start generated code]*/ static PyObject * _io_text_encoding_impl(PyObject *module, PyObject *encoding, int stacklevel) /*[clinic end generated code: output=91b2cfea6934cc0c input=4999aa8b3d90f3d4]*/ { … } /*[clinic input] _io.open_code path : unicode Opens the provided file with the intent to import the contents. This may perform extra validation beyond open(), but is otherwise interchangeable with calling open(path, 'rb'). [clinic start generated code]*/ static PyObject * _io_open_code_impl(PyObject *module, PyObject *path) /*[clinic end generated code: output=2fe4ecbd6f3d6844 input=f5c18e23f4b2ed9f]*/ { … } /* * Private helpers for the io module. */ Py_off_t PyNumber_AsOff_t(PyObject *item, PyObject *err) { … } static int iomodule_traverse(PyObject *mod, visitproc visit, void *arg) { … } static int iomodule_clear(PyObject *mod) { … } static void iomodule_free(void *mod) { … } /* * Module definition */ #define clinic_state … #include "clinic/_iomodule.c.h" #undef clinic_state static PyMethodDef module_methods[] = …; #define ADD_TYPE … static int iomodule_exec(PyObject *m) { … } static struct PyModuleDef_Slot iomodule_slots[] = …; struct PyModuleDef _PyIO_Module = …; PyMODINIT_FUNC PyInit__io(void) { … }
Codebase Browser
cpython